Wind generating set monitoring data validity evaluation method, equipment and medium

Abstract

The invention relates to a wind generating set monitoring data validity evaluation method. The method comprises the following steps: acquiring a linear correlation of monitoring data of a wind generating set in a normal working state; acquiring monitoring data of the wind generating set in real time; preprocessing and cutting the monitoring data, and calculating a Pearson's correlation coefficient and a grey correlation degree between the current monitoring data of different data types; comparing the Pearson correlation coefficient between the monitoring data with the grey correlation degree between the monitoring data sets, and acquiring and recording the linear correlation between the monitoring data; and comparing the linear correlation obtained by real-time calculation with the linear correlation in a normal working state, if the linear correlation changes, determining that the monitoring data is abnormal and giving an alarm, and if the linear correlation does not change, determining that the monitoring data is valid. Compared with the prior art, the method has the advantages that two evaluation indexes of the Pearson correlation coefficient and the grey correlation degree are combined, and the effectiveness of the monitoring data is judged more accurately.

Description

Technical Field

[0001] The present invention relates to the technical field of data fusion, and in particular to a method, device and medium for evaluating the effectiveness of monitoring data of a wind turbine generator set. Background Art

[0002] Under the macro background of global response to climate change and energy transformation, the transition from traditional fossil energy to renewable energy has become inevitable. Wind power generation has become an important force in the field of renewable energy due to its advantages such as rich resources and environmental friendliness. Wind power installed capacity continues to grow rapidly around the world, and large-scale wind turbines are continuously put into use, and their position in the energy supply system is becoming increasingly prominent. The operating environment of wind turbines is extremely complex, and is affected by the interaction of various meteorological factors and their own mechanical and electrical characteristics. External conditions such as intermittent wind speed, variability of wind direction, changes in temperature and air pressure can cause dramatic fluctuations in operating parameters such as output power, speed, and blade force of wind turbines. In order to ensure the efficient and stable operation of wind turbines, reduce the occurrence of failures, and improve power generation efficiency, it is necessary to monitor their operating status in real time and evaluate the data validity so as to take effective maintenance and management measures in a timely manner. Through in-depth analysis of monitoring data, the laws and characteristics behind the data can be excavated, providing strong support for the optimized operation, fault diagnosis, and performance evaluation of wind turbines.

[0003] Since there may be anomalies in the data when it is collected, a single data source cannot judge whether the data is valid by itself, but there are often inherent logical relationships between data of many different parameters, so the validity of the data can be judged based on other parameter data that have strong correlations with it. Traditional methods have certain limitations when dealing with multivariate data with complex correlations. Summary of the invention

[0004] The purpose of the present invention is to overcome the defects of the above-mentioned prior art and to provide a method, device and medium for evaluating the effectiveness of wind turbine monitoring data, so as to explore the linear relationship between different parameters and realize the effectiveness evaluation of wind turbine monitoring data.

[0005] The purpose of the present invention can be achieved by the following technical solutions:

[0006] A method for evaluating the effectiveness of monitoring data of a wind turbine generator set, the method comprising:

[0007] Obtain the linear correlation between monitoring data of various data types under normal working conditions of wind turbines;

[0008] Obtain monitoring data of wind turbines in real time;

[0009] Preprocess and cut the monitoring data to obtain multiple monitoring data sets with equal data volumes of different data types, and calculate the Pearson correlation coefficient between the monitoring data of different data types and the grey correlation between the data sets of different data types;

[0010] Compare the Pearson correlation coefficient between each monitoring data set and the gray correlation degree between each monitoring data set. If the absolute value of the Pearson correlation coefficient between any pair of monitoring data is greater than the preset threshold, the absolute value of the difference between the gray correlation value and the Pearson correlation coefficient is less than the preset deviation value, and both the Pearson correlation coefficient and the gray correlation degree are positive numbers, then it is determined that there is a significant positive linear correlation between the pair of monitoring data. If the absolute value of the Pearson correlation coefficient between any pair of monitoring data is greater than the preset threshold, the absolute value of the difference between the gray correlation value and the Pearson correlation coefficient is less than the preset deviation value, and both the Pearson correlation coefficient and the gray correlation degree are negative numbers, then it is determined that there is a significant positive linear correlation between the pair of monitoring data. There is a significant negative linear correlation between them. If the absolute values ​​of the Pearson correlation coefficient and the gray correlation degree between any pair of monitoring data are both less than the preset threshold and the Pearson correlation coefficient and the gray correlation degree are both positive, it is determined that there is a weak positive linear correlation between the pair of monitoring data. If the absolute values ​​of the Pearson correlation coefficient and the gray correlation degree between any pair of monitoring data are both less than the preset threshold and the Pearson correlation coefficient and the gray correlation degree are both negative, it is determined that there is a weak negative linear correlation between the pair of monitoring data. If the Pearson correlation coefficient and the gray correlation degree between any pair of monitoring data are both 0, it is determined that there is no linear correlation between the pair of monitoring data. The linear correlation between each monitoring data is recorded.

[0011] The linear correlation obtained by real-time calculation is compared with the linear correlation of the monitoring data of various data types under the normal working state. If the linear correlation between any pair of monitoring data changes, it is determined that there is an abnormality in the monitoring data and an alarm is issued. If the linear correlation between the monitoring data remains unchanged, the monitoring data is determined to be valid.

[0012] Furthermore, the monitoring data includes acceleration, tower inclination, temperature and load.

[0013] Furthermore, the preprocessing includes outlier processing, missing value processing and erroneous data correction.

[0014] Furthermore, the calculation formula of the Pearson correlation coefficient is:

[0015]

[0016] Among them, PCC is the Pearson correlation coefficient, n is the sample size, x i and i are the i-th observation values ​​of sample x and sample y respectively, and are the sample means of sample x and sample y respectively.

[0017] Furthermore, the value range of the Pearson correlation coefficient is [-1, 1]. If the calculated Pearson correlation coefficient is greater than or less than the value range, an alarm is issued.

[0018] Furthermore, the calculation process of the grey relational degree between the data sets of different data types includes:

[0019] Obtain multiple monitoring data sets of equal data volume of different data types;

[0020] Arrange the data in the same monitoring data set in the order of collection time to form data columns;

[0021] Any data column is defined as the reference data column, and the other data columns are the comparison data columns. The grey correlation coefficient between the data in each comparison data column and the data in the reference data column is calculated.

[0022] Calculate the average value of the grey correlation coefficient between the data in each comparison data column and the data in the reference data column, and the obtained average value is the grey correlation degree between the comparison data column and the reference data column, that is, the grey correlation degree between the corresponding monitoring data set and the remaining monitoring data sets;

[0023] Repeat the selection and calculation of the above reference data columns to obtain the grey correlation degree between the data sets of different data types.

[0024] Furthermore, the calculation formula of the grey relational coefficient is:

[0025] X 0 =(x 1 , x 2 , …, x n ),

[0026] X i =(x i1 , x i2 , …, x in ), i = 1, 2, ..., m,

[0027] Δ t(i,0) =|x 0 (t)-x i (t)|,

[0028]

[0029] Among them, X 0 is the reference data column, X i is the comparison data column, n is the number of data, m is the number of data types, ρ is the resolution coefficient, Δt(i,0) For each comparison data column X i With reference data column X 0 The absolute difference at time t, Δ max and Δ min are the maximum and minimum values ​​of the absolute difference, respectively.

[0030] Furthermore, if the absolute value of the difference between the Pearson correlation coefficient and the grey correlation degree between any pair of monitoring data is greater than a preset adjustment value, it is determined that the monitoring data is abnormal and an alarm is issued.

[0031] An electronic device comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the above-mentioned method for evaluating the effectiveness of wind turbine generator monitoring data when executing the computer program.

[0032] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the wind turbine generator set monitoring data validity assessment method as described above.

[0033] Compared with the prior art, the beneficial effects of the present invention include:

[0034] 1. The present invention adopts the joint analysis method of Pearson coefficient and grey correlation coefficient to process data from different sensors in real time, utilizes the complex correlation characteristics between wind turbine parameters, explores the linear relationship between different parameters, and compares with the linear correlation under normal working conditions, so as to timely discover the abnormality of monitoring data, so as to realize the real-time effectiveness evaluation of wind turbine monitoring data. When the monitoring data is abnormal, it can timely alarm and remind relevant personnel to deal with it, so as to avoid potential safety hazards; the present invention combines two evaluation indicators, Pearson correlation coefficient and grey correlation degree. Pearson correlation coefficient is mainly used to evaluate the strength and direction of linear correlation, while grey correlation degree can consider the similarity and proximity between data sequences. The combination of the two can more accurately judge the effectiveness of monitoring data, more comprehensively reflect the linear correlation between monitoring data, and at the same time increase the robustness of calculation, further ensuring the accuracy of monitoring;

[0035] 2. The present invention also limits the value of the Pearson correlation coefficient and the difference between the grey correlation coefficient and the Pearson correlation coefficient, so as to more comprehensively detect whether the monitoring data is abnormal and issue an alarm in time. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] Figure 1 A flow chart for evaluating data validity for the present invention;

[0037] Figure 2It is a heat map of the Pearson correlation coefficients between the three variables of the tower partition in one embodiment of the present invention;

[0038] Figure 3 The third acceleration of the tower partition in one embodiment of the present invention is 2, which is a heat map of grey correlation analysis between the reference data column and each variable;

[0039] Figure 4 It is a heat map of the Pearson correlation coefficients between the abnormal variables of the three accelerations 1 in the tower partition in one embodiment of the present invention;

[0040] Figure 5 It is a heat map of grey correlation analysis between the three accelerations 1 of the tower partition and acceleration 2 as reference data columns and various variables in one embodiment of the present invention. DETAILED DESCRIPTION

[0041] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0042] Example 1

[0043] The present invention intends to disclose a method for evaluating the effectiveness of monitoring data of a wind turbine generator set. Since a wind turbine generator set is subject to the interactive influence of multiple meteorological factors and its own mechanical and electrical characteristics, there are multiple inherent logical relationships between multiple data of the wind turbine generator set, such as output power, rotation speed, blade force and other operating parameters. Therefore, the effectiveness of each monitoring data of the wind turbine generator set can be judged based on other parameter data that are strongly correlated with it.

[0044] Wind turbine monitoring data validity assessment method Figure 1 As shown, including:

[0045] Step S1, obtaining the linear correlation between monitoring data of various data types under normal working conditions of a wind turbine generator set.

[0046] The process of obtaining the linear correlation of multiple data types of monitoring data under normal working conditions of wind turbines includes:

[0047] Based on historical operation records, obtain monitoring data of various types of data under normal working conditions of wind turbines;

[0048] Preprocess and cut the monitoring data to obtain multiple monitoring data sets with equal data volumes of different data types;

[0049] Calculate the Pearson correlation coefficient between monitoring data of different data types and the grey correlation between data sets of different data types;

[0050] Compare the Pearson correlation coefficients between the monitoring data and the grey correlation degrees between the monitoring data sets, and record the linear correlation between the samples.

[0051] After obtaining the monitoring data of the normal working state of the wind turbine generator set, the acquisition frequency, accuracy and data format of the monitoring data of different data types are analyzed, the data source is determined and recorded, and after the data preprocessing is completed, the shearing is performed according to the record.

[0052] The calculation formula of Pearson correlation coefficient is:

[0053]

[0054] Among them, PCC is the Pearson correlation coefficient, n is the sample size, x i and i are the i-th observation values ​​of sample x and sample y respectively, and are the sample means of sample x and sample y respectively.

[0055] The calculation process of grey relational degree between data sets of different data types includes:

[0056] Obtain multiple monitoring data sets of equal data volume of different data types;

[0057] Arrange the data in the same monitoring data set in the order of collection time to form data columns;

[0058] Any data column is defined as the reference data column, and the other data columns are the comparison data columns. The grey correlation coefficient between the data in each comparison data column and the data in the reference data column is calculated.

[0059] Calculate the average value of the grey correlation coefficient between the data in each comparison data column and the data in the reference data column, and the obtained average value is the grey correlation degree between the comparison data column and the reference data column, that is, the grey correlation degree between the corresponding monitoring data set and the remaining monitoring data sets;

[0060] Repeat the selection and calculation of the above reference data columns to obtain the grey correlation degree between the data sets of different data types.

[0061] The calculation formula of grey correlation coefficient is:

[0062] X 0 =(x 1 , x 2 , …, x n ),

[0063] X i =(x i1 , x i2 , …, x in ), i = 1, 2, ..., m,

[0064] Δ t(i,0) =|x 0 (t)-x i (t)|,

[0065]

[0066] Among them, X 0 is the reference data column, X i is the comparison data column, n is the number of data, m is the number of data types, ρ is the resolution coefficient, Δ t(i,0) For each comparison data column X i With reference data column X 0 The absolute difference at time t, Δ max and Δ min are the maximum and minimum values ​​of the absolute difference, respectively.

[0067] Step S2, acquiring monitoring data of the wind turbine generator set in real time.

[0068] Monitoring data include acceleration, tower inclination, temperature and load.

[0069] Step S3, preprocessing and cutting the monitoring data, obtaining multiple monitoring data sets of equal data volume of different data types, calculating the Pearson correlation coefficient between the monitoring data of different data types and the grey correlation degree between the data sets of different data types.

[0070] Preprocessing includes outlier processing, missing value processing and erroneous data correction.

[0071] The calculation of the Pearson correlation coefficient is the same as the formula written in step 1 above.

[0072] The value range of the Pearson correlation coefficient is [-1,1]. If the calculated Pearson correlation coefficient is greater than or less than the value range, an alarm is issued.

[0073] The calculation process and formula of the grey correlation degree between data sets of different data types are the same as those described in step 1 above.

[0074] Step S4, compare the Pearson correlation coefficient between each monitoring data and the gray correlation degree between each monitoring data set. If the absolute value of the Pearson correlation coefficient between any pair of monitoring data is greater than the preset threshold, the absolute value of the difference between the gray correlation value and the Pearson correlation coefficient is less than the preset deviation value, and both the Pearson correlation coefficient and the gray correlation degree are positive numbers, it is determined that there is a significant positive linear correlation between the pair of monitoring data. If the absolute value of the Pearson correlation coefficient between any pair of monitoring data is greater than the preset threshold, the absolute value of the difference between the gray correlation value and the Pearson correlation coefficient is less than the preset deviation value, and both the Pearson correlation coefficient and the gray correlation degree are negative numbers , then it is determined that there is a significant negative linear correlation between the pair of monitoring data. If the absolute values ​​of the Pearson correlation coefficient and the gray correlation degree between any pair of monitoring data are both less than the preset threshold and the Pearson correlation coefficient and the gray correlation degree are both positive, then it is determined that there is a weak positive linear correlation between the pair of monitoring data. If the absolute values ​​of the Pearson correlation coefficient and the gray correlation degree between any pair of monitoring data are both less than the preset threshold and the Pearson correlation coefficient and the gray correlation degree are both negative, then it is determined that there is a weak negative linear correlation between the pair of monitoring data. If the Pearson correlation coefficient and the gray correlation degree between any pair of monitoring data are both 0, then it is determined that there is no linear correlation between the pair of monitoring data.

[0075] If the absolute value of the difference between the Pearson correlation coefficient and the grey correlation degree between any pair of monitoring data is greater than a preset adjustment value, it is determined that the monitoring data is abnormal and an alarm is issued.

[0076] Step S5, recording the linear correlation between each monitoring data.

[0077] Step S6, compare the linear correlation obtained by real-time calculation with the linear correlation of the monitoring data of various data types under the normal working state. If the linear correlation between any pair of monitoring data changes, it is determined that there is an abnormality in the monitoring data and an alarm is issued. If the linear correlation between the monitoring data remains unchanged, the monitoring data is determined to be valid.

[0078] This embodiment defines that when |PCC|>0.8 between any two variables, it can be considered that there is a significant linear correlation between the variables. When the wind turbine generator system is operating normally and the monitoring data is correct, if the PCC between the two variables is>0.8, there is a significant positive linear correlation between the variables; if the PCC between the two variables is <-0.8, there is a significant negative linear correlation between the variables; if in a certain set of monitoring data in the future, the PCC value between the two variables is still greater than 0.8 or less than -0.8, it can be determined that the data has a high validity; if the correlation between the two variables changes, that is, the calculated PCC is <0.8 or PCC>-0.8, it indicates that the data of the two variables may be abnormal.

[0079] The following is an example based on actual application scenarios:

[0080] First, the monitoring data of each sensor of the wind turbine generator set is collected, and then the monitoring data is processed: due to the different collection frequencies of different types of data, the acceleration sensor is 100Hz, the inclination sensor is 5Hz, the temperature sensor is 1Hz, and the load sensor is 50Hz. Therefore, 1 data is taken for every 100 acceleration data, 1 data is taken for every 5 tower inclination data, and 1 data is taken for every 50 load data to obtain a data set with equal sample size; then the Pearson correlation coefficient of each variable is calculated to obtain the Pearson correlation coefficient matrix; finally, the Pearson correlation heat map is generated. Figure 2 This is the Pearson correlation heat map of tower partition three. It can be seen from the figure that there is a significant positive linear correlation between acceleration 1 and acceleration 2, inclination 3 and load 5, inclination 3 and load 6, temperature 1 and temperature 2, load 1 and load 2, load 1 and load 3, load 2 and load 3, load 5 and load 6, load 5 and load 7, and load 6 and load 7. Taking acceleration 1 and acceleration 2 of tower partition three as an example, acceleration 2 is set as the reference data column, and the other variables are used as comparison data columns. Ten data samples are taken for each variable to calculate the grey correlation coefficient with acceleration 2 as the reference data column. Figure 3 It is the heat map of grey correlation analysis between the three acceleration columns of the tower partition and each variable. It can be seen from the figure that the grey correlation coefficients of acceleration 1 and acceleration 2 in the ten sample data are all 1, so the grey correlation degree can be calculated to be 1, and the value of the Pearson correlation coefficient between acceleration 1 and acceleration 2 is similar, which verifies that there is a significant positive linear correlation between acceleration 1 and acceleration 2. There is a significant negative linear correlation between acceleration 1 and temperature 1, acceleration 1 and temperature 2, acceleration 2 and temperature 1, acceleration 2 and temperature 2, load 1 and load 5, load 1 and load 6, load 1 and load 7, load 2 and load 5, load 2 and load 6, load 2 and load 7, load 3 and load 5, load 3 and load 6, load 3 and load 7, load 4 and load 8. Similarly, taking acceleration 1 and temperature 1 as an example, acceleration 1 is the reference data column, and ten data are taken as samples of each variable to calculate the grey correlation coefficient with acceleration 1 as the reference data column, and then the grey correlation degree of each comparison data column is calculated. The grey correlation degree of acceleration 1 and temperature 1 is similar to its Pearson correlation coefficient value, which is less than 0.8. Therefore, it can be verified that there is a significant negative linear correlation between acceleration 1 and temperature 1. Figure 4This is the Pearson correlation heat map when the acceleration 1 data of the tower partition 3 is abnormal. It can be seen from the figure that the Pearson correlation coefficient between acceleration 1 and acceleration 2 has dropped from 1 to 0.68. Acceleration 1 and acceleration 2 have changed from a group of variables with significant positive linear correlation to a group of variables with negative correlation. Similarly, acceleration 2 is set as the reference data column, and the other variables are used as comparison data columns. Ten data samples are taken for each variable to calculate the grey correlation coefficient with acceleration 2 as the reference data column. See Figure 5 . Figure 5 and Figure 3 By comparison, we can see that the grey correlation coefficient has also dropped significantly, and the grey correlation degree has also dropped from the previous 1 to 0.6834, which is similar to the data of the Pearson correlation coefficient, verifying the calculation result of the Pearson correlation coefficient, proving that acceleration 1 and acceleration 2 have changed from strongly correlated variables to weakly correlated variables, while the correlation of the other strongly correlated variables remains basically unchanged. It can be judged that there are anomalies in the acceleration 2 data in this set of monitoring data, and the data of the other strongly correlated variables have higher validity.

[0081] Based on the above results, if the correlation coefficients between the strongly correlated variables in the monitoring data fluctuate slightly, and the gray correlation value is similar to the Pearson correlation coefficient value, the data can be considered to have high validity; if the correlation coefficients between some variables deviate significantly, such as the original strong linear correlation becomes a weak linear correlation, and the positive linear correlation becomes a negative linear correlation, it indicates that the data group may have data anomalies. This innovative method can help engineers better understand the internal connection between the various parameters of wind turbines, establish an accurate validity evaluation model, and realize the validity evaluation of wind turbine monitoring data.

[0082] Example 2

[0083] Based on Example 1, this embodiment provides an electronic device, including: one or more processors and a memory, wherein the memory stores one or more programs, and the one or more programs include instructions for executing the aforementioned wind turbine monitoring data validity assessment method.

[0084] At the hardware level, the electronic device includes a processor, an internal bus, a network interface, a memory, and a non-volatile memory, and may also include hardware required for other services. The processor reads the corresponding computer program from the non-volatile memory into the memory and then runs it to implement the above-mentioned wind turbine monitoring data validity assessment method. Of course, in addition to the software implementation, the present invention does not exclude other implementation methods, such as logic devices or a combination of software and hardware, etc., that is to say, the execution subject of the following processing flow is not limited to each logic unit, but can also be hardware or logic devices.

[0085] The memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0086] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0087] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed by the present invention, and these modifications or replacements should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention shall be based on the protection scope of the claims.

Claims

1. A method for evaluating the effectiveness of wind turbine monitoring data, characterized in that: The method comprises: Obtain the linear correlation between monitoring data of various data types under normal working conditions of wind turbines; Obtain monitoring data of wind turbines in real time; Preprocess and cut the monitoring data to obtain multiple monitoring data sets with equal data volumes of different data types, and calculate the Pearson correlation coefficient between the monitoring data of different data types and the grey correlation between the data sets of different data types; Compare the Pearson correlation coefficient between each monitoring data set and the gray correlation degree between each monitoring data set. If the absolute value of the Pearson correlation coefficient between any pair of monitoring data is greater than the preset threshold, the absolute value of the difference between the gray correlation value and the Pearson correlation coefficient is less than the preset deviation value, and both the Pearson correlation coefficient and the gray correlation degree are positive numbers, then it is determined that there is a significant positive linear correlation between the pair of monitoring data. If the absolute value of the Pearson correlation coefficient between any pair of monitoring data is greater than the preset threshold, the absolute value of the difference between the gray correlation value and the Pearson correlation coefficient is less than the preset deviation value, and both the Pearson correlation coefficient and the gray correlation degree are negative numbers, then it is determined that there is a significant positive linear correlation between the pair of monitoring data. There is a significant negative linear correlation between them. If the absolute values ​​of the Pearson correlation coefficient and the gray correlation degree between any pair of monitoring data are both less than the preset threshold and the Pearson correlation coefficient and the gray correlation degree are both positive, it is determined that there is a weak positive linear correlation between the pair of monitoring data. If the absolute values ​​of the Pearson correlation coefficient and the gray correlation degree between any pair of monitoring data are both less than the preset threshold and the Pearson correlation coefficient and the gray correlation degree are both negative, it is determined that there is a weak negative linear correlation between the pair of monitoring data. If the Pearson correlation coefficient and the gray correlation degree between any pair of monitoring data are both 0, it is determined that there is no linear correlation between the pair of monitoring data. The linear correlation between each monitoring data is recorded. The linear correlation obtained by real-time calculation is compared with the linear correlation of the monitoring data of various data types under the normal working state. If the linear correlation between any pair of monitoring data changes, it is determined that there is an abnormality in the monitoring data and an alarm is issued. If the linear correlation between the monitoring data remains unchanged, the monitoring data is determined to be valid.

2. A wind turbine generator monitoring data validity assessment method according to claim 1, characterized in that: The monitoring data include acceleration, tower inclination, temperature and load.

3. A method for evaluating the effectiveness of wind turbine monitoring data according to claim 1, characterized in that: The preprocessing includes outlier processing, missing value processing and erroneous data correction.

4. A method for evaluating the effectiveness of wind turbine generator monitoring data according to claim 1, characterized in that: The calculation formula of the Pearson correlation coefficient is: Among them, PCC is the Pearson correlation coefficient, n is the sample size, x i and i are the i-th observation values ​​of sample x and sample y respectively, and are the sample means of sample x and sample y respectively.

5. A method for evaluating the effectiveness of wind turbine monitoring data according to claim 1, characterized in that: The value range of the Pearson correlation coefficient is [-1,1]. If the calculated Pearson correlation coefficient is greater than or less than the value range, an alarm is issued.

6. A method for evaluating the effectiveness of wind turbine generator monitoring data according to claim 1, characterized in that: The calculation process of the grey relational degree between the data sets of different data types includes: Obtain multiple monitoring data sets of equal data volume of different data types; Arrange the data in the same monitoring data set in the order of collection time to form data columns; Any data column is defined as the reference data column, and the other data columns are the comparison data columns. The grey correlation coefficient between the data in each comparison data column and the data in the reference data column is calculated. Calculate the average value of the grey correlation coefficient between the data in each comparison data column and the data in the reference data column, and the obtained average value is the grey correlation degree between the comparison data column and the reference data column, that is, the grey correlation degree between the corresponding monitoring data set and the remaining monitoring data sets; Repeat the selection and calculation of the above reference data columns to obtain the grey correlation degree between the data sets of different data types.

7. A method for evaluating the effectiveness of wind turbine generator monitoring data according to claim 6, characterized in that: The calculation formula of the grey correlation coefficient is: X0=(x1,x2,...,x n ), X i =(x i1 ,x i2 ,…,x in ),i=1,2,…,m, Δ t(i,0) =|x0(t)-x i (t)|, Among them, X0 is the reference data column, X i is the comparison data column, n is the number of data, m is the number of data types, ρ is the resolution coefficient, Δ t(i,0) For each comparison data column X i The absolute difference with the reference data column X0 at time point t, Δ max and Δ min are the maximum and minimum values ​​of the absolute difference, respectively.

8. A method for evaluating the effectiveness of wind turbine generator monitoring data according to claim 1, characterized in that: If the absolute value of the difference between the Pearson correlation coefficient and the grey correlation degree between any pair of monitoring data is greater than a preset adjustment value, it is determined that the monitoring data is abnormal and an alarm is issued.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the method for evaluating the effectiveness of wind turbine generator monitoring data as described in any one of claims 1 to 8 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method for evaluating the effectiveness of wind turbine generator monitoring data as described in any one of claims 1 to 8 are implemented.

Images